source-to-notes
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, such as articles, video transcripts, and web pages, which serves as an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read text, transcripts, or links provided by the user (SKILL.md).
- Boundary markers: The instructions lack explicit boundary markers (e.g., delimiters) or safety warnings to ignore instructions embedded within the analyzed source content.
- Capability inventory: The skill can perform file-write operations by saving generated notes to a connected notes application, such as the Scratchpad connector (SKILL.md).
- Sanitization: There is no evidence of input sanitization or filtering to prevent the agent from following instructions found within the source material.
Audit Metadata